© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95168
    Prev
    Next
    INDEX
    Explanations

    pow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ยัง
    -0.08
    ροσ
    -0.07
    teurs
    -0.07
    -debug
    -0.07
    ছ
    -0.07
    UV
    -0.07
    ผ
    -0.07
     หรือ
    -0.07
     unchanged
    -0.07
     dub
    -0.07
    POSITIVE LOGITS
     footsteps
    0.09
     haste
    0.08
    kasten
    0.07
    十
    0.07
    轨
    0.07
     fumes
    0.07
    овую
    0.07
     incidente
    0.07
     كلمة
    0.07
     industry's
    0.07
    Activations Density 0.001%

    No Known Activations